Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare destructiveHint=false and readOnlyHint=false; the description supplies the real behavioral picture: items move to Recently deleted rather than being destroyed, are recoverable via restore_asset for 30 days, and continue playing/exporting in projects that use them. That soft-delete semantics is consistent with destructiveHint=false, and the required user confirmation plus dryRun preflight is context the annotations do not convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The action and its consequence are front-loaded in the first clause, and every sentence carries distinct information (recovery window, project impact, confirmation, alternative tool). Some phrasing is awkward and nested — 'assetId from list_media from: folder or workspace' and 'dryRun: true says' read like compressed notes rather than prose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter, no-output-schema mutation tool, the description covers what is removed, where it goes, how long it is recoverable, the effect on dependent projects, the required user confirmation, and the sibling alternative. Nothing an agent needs in order to call this safely is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50% — dryRun is documented in the schema, assetIds is not. The description compensates by naming assetIds' provenance ('assetId from list_media from: folder or workspace') and restating dryRun's meaning as a count-only preflight. It could still say more about the 200-item cap or what an invalid assetId yields, so it stops short of full coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Delete files from the workspace's library', and immediately scopes it as library-level removal rather than project-level. It explicitly names the sibling it is not ('remove_media') and the recovery counterpart ('restore_asset'), so an agent can distinguish it from adjacent tools without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit routing rule: to remove a file from this project only, use remove_media; to undo, use restore_asset. It also adds a procedural prerequisite — 'Ask the user first, saying how many projects use each' — and points at dryRun as the way to obtain that count, which is unusually actionable guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.